INDEX

Explanations

technical terms related to app development

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cala

-0.17

elman

-0.15

erty

-0.15

 Griffin

-0.14

moth

-0.14

Sez

-0.14

ivar

-0.14

Duo

-0.14

lixir

-0.14

 zoekt

-0.14

POSITIVE LOGITS

/Area

0.18

yÅ¡

0.17

 stereotype

0.16

–↵↵

0.16

Blank

0.15

flip

0.15

ITA

0.14

Ve

0.14

 stere

0.14

 canonical

0.14

Activations Density 0.006%

technical terms related to app development

No Comments

No Known Activations